Devices, methods and systems for transmitting signals through a device located in a blood vessel of an animal, for stimulating and/or sensing activity of media proximal to the device, wherein the media includes tissue and/or fluid.
Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A method of controlling an apparatus in communication with a brain machine interface, the method comprising: measuring a first neural activity in a first neural area, where the first neural activity is associated with a first intent to control the apparatus, where measuring the first neural activity comprises using a first sensor of the brain machine interface; measuring a second neural activity in a second neural area using a second sensor of the brain machine interface; receiving, via a processor in wired or wireless communication with the brain machine interface, the first neural activity and the second neural activity; processing, via the processor, the received first neural activity and the second neural activity; creating and delivering, via the processor, one or more first control signals to the apparatus upon comparing the second neural activity with the first neural activity, and confirming, based on this comparison, that the second neural activity is associated with the first intent; determining, via the processor, a desired parameter of the apparatus from a signal received from a sensor of the apparatus; calculating, via the processor, a control correlation between the measured first neural activity and the desired parameter; and adjusting, via the processor, a brain machine interface control percentage of the apparatus and an apparatus control percentage of the apparatus upon determining the control correlation is below a predetermined error, where the brain machine interface control percentage is the percentage control of the apparatus via signals detected by the first and second sensors of the brain machine interface, and where the apparatus control percentage of the apparatus is the percentage control of the apparatus via signals detected by the sensor of the apparatus, and where the adjusting comprises increasing the brain machine interface control percentage and decreasing the apparatus control percentage upon determining the control correlation is below the predetermined error and/or where the adjusting comprises decreasing the brain machine interface control percentage and increasing the apparatus control percentage upon determining the control correlation is above the predetermined error.
This invention relates to brain-machine interface (BMI) systems for controlling external apparatuses, addressing the challenge of accurately interpreting neural signals to ensure reliable device operation. The method involves measuring neural activity from two distinct brain regions using separate sensors in a BMI system. The first neural activity, detected in a primary neural area, corresponds to a user's intent to control an apparatus. The second neural activity, measured in a secondary neural area, is used to confirm the intent by comparing it to the first signal. If the comparison validates the intent, the system generates control signals for the apparatus. Additionally, the system receives feedback from an apparatus sensor to determine a desired operational parameter. By calculating the correlation between the measured neural activity and this parameter, the system dynamically adjusts the balance between BMI-based control and apparatus-based control. If the correlation is below a predetermined error threshold, the system increases reliance on BMI signals and reduces reliance on apparatus feedback, and vice versa if the correlation exceeds the threshold. This adaptive approach improves the accuracy and responsiveness of BMI-controlled devices by continuously optimizing the contribution of neural and apparatus-derived control inputs.
2. The method of claim 1 , further comprising: decoding, via the processor, the first intent from the measured first neural activity; and decoding, via the processor, a second intent from the measured second neural activity, where the delivering comprises delivering the one or more first control signals to the apparatus upon confirming that the second intent is associated with the first intent.
This invention relates to a neural interface system for decoding and acting on user intentions based on neural activity. The system addresses the challenge of accurately interpreting neural signals to control external devices, particularly ensuring that detected intentions are validated before triggering actions. The method involves measuring neural activity from a user, where the activity corresponds to at least two distinct intents. A processor decodes the first intent from the first measured neural activity and the second intent from the second measured neural activity. The system then delivers control signals to an apparatus only after confirming that the second intent is associated with the first intent, ensuring that the action is intentional and not a false positive. This validation step enhances reliability by requiring multiple neural signals to align before executing a command, reducing errors in device control. The apparatus may include robotic limbs, prosthetics, or other assistive technologies, enabling more precise and safe interaction based on neural commands. The system improves upon prior art by incorporating a dual-intent verification mechanism, which minimizes unintended activations and improves user trust in neural interfaces.
3. The method of claim 2 , where decoding the first and second intents comprises referencing previously measured neural activities stored in a memory.
A system and method for decoding neural activities to determine user intents involves analyzing brain signals to identify and distinguish between multiple user intents. The method captures neural activities generated by a user's brain, processes these signals to extract relevant features, and decodes them to determine the user's intended actions or commands. The decoding process involves comparing the captured neural activities with previously measured and stored neural activity patterns in a memory. By referencing these stored patterns, the system can accurately interpret the user's current neural signals to identify specific intents. This approach enables real-time or near-real-time interpretation of brain signals for applications such as brain-computer interfaces, assistive technologies, or neural prosthetics. The system may also include preprocessing steps to enhance signal quality and reduce noise, ensuring reliable intent detection. The method supports the decoding of multiple distinct intents, allowing for complex interactions or control commands based on neural activity. The stored neural activity patterns serve as a reference database, enabling the system to match and classify incoming signals with high accuracy. This technology addresses the challenge of accurately interpreting neural signals in real-world applications, where signal variability and noise can complicate intent detection.
4. The method of claim 1 , further comprising repeating the measuring until at least one of the one or more first control signals is delivered to the apparatus.
A system and method for controlling an apparatus involves measuring one or more operational parameters of the apparatus to determine its state. The system generates one or more first control signals based on the measured parameters to adjust the apparatus's operation. These control signals are delivered to the apparatus to modify its behavior. The method includes repeating the measurement process until at least one of the first control signals is successfully delivered to the apparatus. This ensures continuous monitoring and adjustment of the apparatus to maintain desired performance or correct deviations. The system may also generate one or more second control signals based on the measured parameters, which are delivered to a user interface to provide feedback or alerts. The feedback may include visual, auditory, or haptic signals to inform the user of the apparatus's status or required actions. The method ensures real-time control and monitoring, improving operational efficiency and safety. The apparatus may be any device requiring dynamic adjustment, such as industrial machinery, medical equipment, or automotive systems. The system may also include a processor to execute the control logic and a communication interface to transmit the control signals. The repeated measurement and adjustment process ensures continuous optimization of the apparatus's performance.
5. The method of claim 1 , where the delivering comprises delivering the one or more first control signals to the apparatus to control a first parameter and/or a second parameter of the apparatus.
This invention relates to a method for controlling an apparatus by delivering control signals to adjust specific operational parameters. The technology domain involves automated control systems, where precise regulation of apparatus parameters is essential for optimal performance. The problem addressed is the need for flexible and efficient control mechanisms that can independently or jointly adjust multiple parameters of an apparatus to achieve desired operational states. The method involves delivering one or more control signals to the apparatus to regulate at least one of two distinct parameters. The first parameter may relate to a primary operational characteristic, such as temperature, pressure, or speed, while the second parameter could involve a secondary characteristic, such as flow rate, voltage, or positional alignment. The control signals are designed to independently or simultaneously adjust these parameters, allowing for fine-tuned control based on real-time feedback or predefined settings. This approach enhances system responsiveness and adaptability, ensuring the apparatus operates within specified tolerances or performance thresholds. The method may be applied in various industrial, medical, or consumer electronics contexts where multi-parameter control is critical. By enabling dynamic adjustments, the invention improves efficiency, accuracy, and reliability in apparatus operation. The control signals can be generated by a central processing unit or a dedicated controller, which processes input data to determine the necessary adjustments for the apparatus parameters. This ensures seamless integration with existing control systems while providing enhanced functionality.
6. The method of claim 1 , where the first sensor is proximate or in a first neural area and where the second sensor is proximate or in a second neural area.
This invention relates to a neural monitoring system that uses multiple sensors to detect and analyze neural activity in different brain regions. The system addresses the challenge of obtaining precise, localized neural data to improve diagnostics, treatment planning, or brain-computer interface applications. The method involves deploying at least two sensors in or near distinct neural areas of the brain. The first sensor is positioned proximate to or within a first neural area, while the second sensor is placed proximate to or within a second neural area. These sensors capture neural signals, such as electrical activity or biochemical changes, from their respective locations. The system may process these signals to compare neural activity between the two regions, identify patterns, or correlate data with specific cognitive or physiological functions. This approach enables targeted monitoring of brain function, which can be critical for applications like epilepsy management, deep brain stimulation, or neuroprosthetic control. The sensors may be implanted or external, depending on the application, and could include electrodes, optical sensors, or other neural recording devices. The system may also incorporate signal processing techniques to enhance data accuracy and interpretability. By analyzing signals from multiple neural areas, the invention provides a more comprehensive understanding of brain function compared to single-sensor systems. This can lead to more effective interventions or adaptive control mechanisms in neural interfaces.
7. The method of claim 6 , wherein the first and second neural areas are in a brain.
This technical summary describes a method for analyzing neural activity in the brain to detect or predict specific cognitive or physiological states. The method involves monitoring electrical signals from two distinct neural areas within the brain, where these areas are associated with different functions or regions. The signals are processed to identify patterns or correlations that indicate a particular state, such as a neurological disorder, cognitive function, or response to a stimulus. The method may include preprocessing the signals to remove noise, extracting relevant features, and applying machine learning or statistical techniques to classify or predict the state based on the neural activity. The neural areas may be selected based on their known roles in brain function, such as motor control, sensory processing, or emotional regulation. The method can be used in medical diagnostics, brain-computer interfaces, or neurofeedback systems to improve understanding or treatment of neurological conditions. The approach leverages the spatial and temporal dynamics of brain activity to provide insights into how different regions interact and contribute to behavior or pathology.
8. The method of claim 1 , where the brain machine interface control percentage is initially 0% to 25% and the apparatus control percentage is initially 75% to 100%, further comprising incrementally increasing the brain machine interface control percentage from an initial percentage of 0% to 25% to a final percentage of 75% to 100%.
This invention relates to brain-machine interfaces (BMIs) for controlling apparatuses, addressing the challenge of transitioning control from traditional apparatus-based systems to brain-controlled systems. The method involves a gradual shift in control authority from the apparatus to the brain-machine interface (BMI). Initially, the BMI has minimal control (0% to 25%), while the apparatus retains the majority (75% to 100%). Over time, the BMI's control percentage increases incrementally until it reaches a dominant role (75% to 100%), while the apparatus's control decreases proportionally. This gradual transition allows users to adapt to brain-controlled operations without abrupt changes, improving safety and usability. The system may include feedback mechanisms to monitor performance and adjust the transition rate based on user proficiency. The method ensures a smooth handover of control, reducing errors and enhancing user confidence in BMI-driven systems. Applications include medical prosthetics, assistive devices, and other systems where precise, adaptive control is required.
9. The method of claim 1 , wherein the brain machine interface control percentage of the apparatus is associated with a user of the apparatus using the brain machine interface such that the brain machine interface is configured to record, via the first or second sensor, brain activity of the user when the user attempts to control the apparatus, and wherein the apparatus control percentage of the apparatus is associated with the apparatus such that the apparatus determines, via an apparatus processor, an estimate of the first parameter.
A brain-machine interface (BMI) system is used to control an apparatus based on a user's brain activity. The system includes sensors to detect brain signals and an apparatus processor to interpret these signals. The invention addresses the challenge of accurately associating control inputs with either the user's brain activity or the apparatus itself, ensuring reliable operation. The BMI records brain activity when the user attempts to control the apparatus, allowing the system to determine the user's intent. The apparatus processor estimates a parameter, such as control authority or signal strength, to determine the proportion of control attributed to the user versus the apparatus. This ensures that the apparatus can adjust its response based on the user's brain signals while maintaining stability. The system dynamically balances control between the user and the apparatus, improving accuracy and reducing errors in interpretation. This approach is particularly useful in applications where precise control is required, such as medical devices or assistive technologies. The invention enhances the reliability of BMI systems by distinguishing between user-intended actions and system-generated responses.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
August 3, 2018
December 24, 2019
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.